The rise of deep learning and transformations in bioactivity prediction power of molecular modeling tools

The search and design for the better use of bioactive compounds are used in many experiments to best mimic compounds' functions in the human body. However, finding a cost-effective and timesaving approach is a top priority in different disciplines. Nowadays, artificial intelligence (AI) and particularly deep learning (DL) methods are widely applied to improve the precision and accuracy of models used in the drug discovery process. DL approaches have been used to provide more opportunities for a faster, efficient, cost-effective, and reliable computer-aided drug discovery. Moreover, the increasing biomedical data volume in areas, like genome sequences, medical images, protein structures, etc., has made data mining algorithms very important in finding novel compounds that could be drugs, uncovering or repurposing drugs and improving the area of genetic markers-based personalized medicine. Furthermore, deep neural networks (DNNs) have been demonstrated to outperform other techniques such as random forests and SVMs for QSAR studies and ligand-based virtual screening. Despite this, in QSAR studies, the quality of different data sources and potential experimental errors has greatly affected the accuracy of QSAR predictions. Therefore, further researches are still needed to improve the accuracy, selectivity, and sensitivity of the DL approach in building the best models of drug discovery.

Future directions of chemical theory and computation

Theoretical and computational chemistry aims to develop chemical theory and to apply numerical computation and simulation to reveal the mechanism behind complex chemical phenomena via quantum theory and statistical mechanics. Computation is the third pillar of scientific research together with theory and experiment. Computation enables scientists to test, discover, and build models/theories of the corresponding chemical phenomena. Theoretical and computational chemistry has been advanced to a new era due to the development of high-performance computational facilities and artificial intelligence approaches. The tendency to merge electronic structural theory with quantum chemical dynamics and statistical mechanics is of increasing interest because of the rapid development of on-the-fly dynamic simulations for complex systems plus low-scaling electronic structural theory. Another challenging issue lies in the transition from order to disorder, from thermodynamics to dynamics, and from equilibrium to non-equilibrium. Despite an increasingly rapid emergence of advances in computational power, detailed criteria for databases, effective data sharing strategies, and deep learning workflows have yet to be developed. Here, we outline some challenges and limitations of the current artificial intelligence approaches with an outlook on the potential future directions for chemistry in the big data era.

Simulated training model in a low cost for laparoscopic inguinal hernioplasty

Purpose

Develop a 3D model for the simulation of laparoscopic inguinal hernioplasty transabdominal preperitoneal (TAPP).

Methods

This is an experimental study, 18 participants were selected, divided into three groups, experimental (GE) surgeons in training, control (GC) experienced surgeons and Shaw (GS) nonexperienced surgeons. The simulation in the 3D model was carried out in 6 sessions fulfilling the 5 stages. Opening the peritoneum with the creation of the preperitoneal space; identification of important structures; hernia identification and reduction; placement and fixation of the mesh in Cooper’s ligament and closure of the peritoneum.

Results

In the 1st stage, the GE obtained an average of 1.25 ± 0.42 in the 1st session and 3.25 ± 0.62 in the 6th session (p = 0.05) and in the 5th stage 0.91 ± 0.29 in the first session. 1st session and 1.91 ± 0.29 in the 6th session (p = 0.001), with no significant difference between groups. The learning and skill curve in the SG represented 1.08 ± 0.29 1st and 3.50 ± 0.90 6th session (p = 0.001).

Conclusions

The creation of a systematization of training in simulation applied to the three-dimensional model enabled gain in laparoscopic skills and underpinned its theoretical and practical foundations.

Deep Learning in Drug Discovery and Medicine; Scratching the Surface

The practice of medicine is ever evolving. Diagnosing disease, which is often the first step in a cure, has seen a sea change from the discerning hands of the neighborhood physician to the use of sophisticated machines to use of information gleaned from biomarkers obtained by the most minimally invasive of means. The last 100 or so years have borne witness to the enormous success story of allopathy, a practice that found favor over earlier practices of medical purgatory and homeopathy. Nevertheless, failures of this approach coupled with the omics and bioinformatics revolution spurred precision medicine, a platform wherein the molecular profile of an individual patient drives the selection of therapy. Indeed, precision medicine-based therapies that first found their place in oncology are rapidly finding uses in autoimmune, renal and other diseases. More recently a new renaissance that is shaping everyday life is making its way into healthcare. Drug discovery and medicine that started with Ayurveda in India are now benefiting from an altogether different artificial intelligence (AI)-one which is automating the invention of new chemical entities and the mining of large databases in health-privacy-protected vaults. Indeed, disciplines as diverse as language, neurophysiology, chemistry, toxicology, biostatistics, medicine and computing have come together to harness algorithms based on transfer learning and recurrent neural networks to design novel drug candidates, a priori inform on their safety, metabolism and clearance, and engineer their delivery but only on demand, all the while cataloging and comparing omics signatures across traditionally classified diseases to enable basket treatment strategies. This review highlights inroads made and being made in directed-drug design and molecular therapy.

De Novo Design at the Edge of Chaos

Computational medicinal chemistry offers viable strategies for finding, characterizing, and optimizing innovative pharmacologically active compounds. Technological advances in both computer hardware and software as well as biological chemistry have enabled a renaissance of computer-assisted "de novo" design of molecules with desired pharmacological properties. Here, we present our current perspective on the concept of automated molecule generation by highlighting chemocentric methods that may capture druglike chemical space, consider ligand promiscuity for hit and lead finding, and provide fresh ideas for the rational design of customized screening of compound libraries.

Predicting Melting Points of Organic Molecules: Applications to Aqueous Solubility Prediction Using the General Solubility Equation

In this work we make predictions of several important molecular properties of academic and industrial importance to seek answers to two questions: 1) Can we apply efficient machine learning techniques, using inexpensive descriptors, to predict melting points to a reasonable level of accuracy? 2) Can values of this level of accuracy be usefully applied to predicting aqueous solubility? We present predictions of melting points made by several novel machine learning models, previously applied to solubility prediction. Additionally, we make predictions of solubility via the General Solubility Equation (GSE) and monitor the impact of varying the logP prediction model (AlogP and XlogP) on the GSE. We note that the machine learning models presented, using a modest number of 2D descriptors, can make melting point predictions in line with the current state of the art prediction methods (RMSE≥40 °C). We also find that predicted melting points, with an RMSE of tens of degrees Celsius, can be usefully applied to the GSE to yield accurate solubility predictions (log10 S RMSE<1) over a small dataset of drug-like molecules.

Uniting cheminformatics and chemical theory to predict the intrinsic aqueous solubility of crystalline druglike molecules

We present four models of solution free-energy prediction for druglike molecules utilizing cheminformatics descriptors and theoretically calculated thermodynamic values. We make predictions of solution free energy using physics-based theory alone and using machine learning/quantitative structure–property relationship (QSPR) models. We also develop machine learning models where the theoretical energies and cheminformatics descriptors are used as combined input. These models are used to predict solvation free energy. While direct theoretical calculation does not give accurate results in this approach, machine learning is able to give predictions with a root mean squared error (RMSE) of ∼1.1 log S units in a 10-fold cross-validation for our Drug-Like-Solubility-100 (DLS-100) dataset of 100 druglike molecules. We find that a model built using energy terms from our theoretical methodology as descriptors is marginally less predictive than one built on Chemistry Development Kit (CDK) descriptors. Combining both sets of descriptors allows a further but very modest improvement in the predictions. However, in some cases, this is a statistically significant enhancement. These results suggest that there is little complementarity between the chemical information provided by these two sets of descriptors, despite their different sources and methods of calculation. Our machine learning models are also able to predict the well-known Solubility Challenge dataset with an RMSE value of 0.9–1.0 log S units.

The Structure, Thermodynamics and Solubility of Organic Crystals from Simulation with a Polarizable Force Field

An important unsolved problem in materials science is prediction of the thermodynamic stability of organic crystals and their solubility from first principles. Solubility can be defined as the saturating concentration of a molecule within a liquid solvent, where the physical picture is of solvated molecules in equilibrium with their solid phase. Despite the importance of solubility in determining the oral bioavailability of pharmaceuticals, prediction tools are currently limited to quantitative structure-property relationships that are fit to experimental solubility measurements. For the first time, we describe a consistent procedure for the prediction of the structure, thermodynamic stability and solubility of organic crystals from molecular dynamics simulations using the polarizable multipole AMOEBA force field. Our approach is based on a thermodynamic cycle that decomposes standard state solubility into the sum of solid-vapor sublimation and vapor-liquid solvation free energies [Formula: see text], which are computed via the orthogonal space random walk (OSRW) sampling strategy. Application to the n-alkylamides series from aeetamide through octanamide was selected due to the dependence of their solubility on both amide hydrogen bonding and the hydrophobic effect, which are each fundamental to protein structure and solubility. On average, the calculated absolute standard state solubility free energies are accurate to within 1.1 kcal/mol. The experimental trend of decreasing solubility as a function of n-alkylamide chain length is recapitulated by the increasing stability of the crystalline state and to a lesser degree by decreasing favorability of solvation (i.e. the hydrophobic effect). Our results suggest that coupling the polarizable AMOEBA force field with an orthogonal space based free energy algorithm, as implemented in the program Force Field X, is a consistent procedure for predicting the structure, thermodynamic stability and solubility of organic crystals.